Instructions to use gradientai/Llama-3-8B-Instruct-262k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gradientai/Llama-3-8B-Instruct-262k with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="gradientai/Llama-3-8B-Instruct-262k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gradientai/Llama-3-8B-Instruct-262k")
model = AutoModelForCausalLM.from_pretrained("gradientai/Llama-3-8B-Instruct-262k", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gradientai/Llama-3-8B-Instruct-262k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gradientai/Llama-3-8B-Instruct-262k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gradientai/Llama-3-8B-Instruct-262k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gradientai/Llama-3-8B-Instruct-262k

SGLang

How to use gradientai/Llama-3-8B-Instruct-262k with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "gradientai/Llama-3-8B-Instruct-262k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gradientai/Llama-3-8B-Instruct-262k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "gradientai/Llama-3-8B-Instruct-262k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gradientai/Llama-3-8B-Instruct-262k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gradientai/Llama-3-8B-Instruct-262k with Docker Model Runner:
```
docker model run hf.co/gradientai/Llama-3-8B-Instruct-262k
```

ITS NOT REAL

#15

by rombodawg - opened May 2, 2024

Discussion

rombodawg

May 2, 2024

vihangsharma

May 2, 2024

scam?

rombodawg

May 2, 2024

@vihangsharma they had a nice reply here
https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k/discussions/11

michaelfeil

May 3, 2024

Hey, @vihangsharma as mentioned in the other threads we have worked on better alignment.

@rombodawg We liked your meme!

https://huggingface.co/gradientai/Llama-3-70B-Instruct-Gradient-262k Let us know if you are interested in doing the same for 8B.

rombodawg

May 3, 2024

Hey, @vihangsharma as mentioned in the other threads we have worked on better alignment.

@rombodawg We liked your meme!

https://huggingface.co/gradientai/Llama-3-70B-Instruct-Gradient-262k Let us know if you are interested in doing the same for 8B.

I would love to see 8b have the same effectiveness at extremely high context inference as the 70b. The majority of the open source community is running modest hardware, at most a rtx 3090 with 24gb of vram, but evem thats rare, an update to the 8b-instruct model would be astounding

koesn

Jun 1, 2024

•

edited Jun 2, 2024

Much appreciate to Gradient team, thank's for this amazing model. I haven't tried to the extent over 100k tokens. But I'm actively using ±26k-±100k input including very long system prompt, exactly as Mark said about this use case. Miqu is great on handling those scenario, but it's 32k is very limiting so I have to back and forth to GPT-4o. Now Gradient 70b 262k fill the gaps and I replaced Miqu with it. Now I'm happily using Gradient's 262k to process my ±100k tokens system prompt. Gradient's legacy brings new possibilities.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment